metadata
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: Llama-3.1-8B-Instruct-PsyCourse-doc-fold10
results: []
Llama-3.1-8B-Instruct-PsyCourse-doc-fold10
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the course-doc-train-fold10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0578
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1641 | 0.3951 | 10 | 0.1373 |
| 0.0909 | 0.7901 | 20 | 0.0855 |
| 0.0908 | 1.1852 | 30 | 0.0701 |
| 0.118 | 1.5802 | 40 | 0.0646 |
| 0.0867 | 1.9753 | 50 | 0.0616 |
| 0.0622 | 2.3704 | 60 | 0.0601 |
| 0.0977 | 2.7654 | 70 | 0.0595 |
| 0.1045 | 3.1605 | 80 | 0.0584 |
| 0.0473 | 3.5556 | 90 | 0.0583 |
| 0.0568 | 3.9506 | 100 | 0.0580 |
| 0.0772 | 4.3457 | 110 | 0.0578 |
| 0.0765 | 4.7407 | 120 | 0.0578 |
Framework versions
- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3